prepare_attested_computation

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value beyond these by stating that the tool does not execute the computation ('non-executing') and does not echo parameter values, which has privacy/security implications. It also implies validation ('Check declared parameters'), though it does not explicitly describe error behavior. No contradiction exists between description and annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is entirely functional: it states the action, the object, the output, and a critical behavioral constraint. It is front-loaded with the primary action and has zero unnecessary words. This is exemplary conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should explain what the tool returns. It mentions 'produce non-executing digests' but does not specify the digest format, whether a receipt or error is returned, or what 'declared parameters' implies beyond the schema. Given the tool's role in attested computations and the availability of sibling tools like check_computation_receipt, the lack of explicit output details leaves some ambiguity for an agent deciding how to use the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: 'uri' is described as 'Canonical or compatibility URI of the Attested Computation.', 'asOf' as 'UTC ISO date or datetime for freshness evaluation.', and 'parameters' as 'Parameter values keyed only by declared names.' The description adds no additional meaning beyond these, so the baseline of 3 is appropriate. It does not clarify formats or edge cases beyond the schema's descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Check declared parameters and produce non-executing digests') and the resource ('Attested Computation'), and adds a critical constraint ('without echoing parameter values'). This distinguishes it from siblings like inspect_attested_computation (which inspects existing computations) and check_computation_receipt (which checks receipts). The verb 'produce' and the specific output 'digests' make the tool's function unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus its siblings. It does not mention prerequisites (e.g., whether the URI must reference an existing computation), nor does it suggest a workflow context (e.g., 'use this before submitting for verification'). The description only states what it does, leaving the agent to infer appropriate usage from the name and sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.